Multi LLM — AI skill for Claude Code
Parallel multi-LLM analysis — spawn Codex + Kimi + Gemini CLIs, compare with Claude.
How to install Multi LLM
Installs to ~/.claude/skills/howardpen9-claude-code-multi-llm-multi-llm/SKILL.md
mkdir -p ~/.claude/skills/howardpen9-claude-code-multi-llm-multi-llm && curl -fsSL https://raw.githubusercontent.com/howardpen9/claude-code-multi-llm/HEAD/commands/multi-llm.md -o ~/.claude/skills/howardpen9-claude-code-multi-llm-multi-llm/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Multi LLM does
description: Parallel multi-LLM analysis — spawn Codex + Kimi + Gemini CLIs, compare with Claude allowed-tools: Bash(codex *), Bash(kimi *), Bash(gemini *), Bash(which *), Bash(cat *), Bash(mktemp *), Bash(rm *), Bash(git *), Agent, Read, Grep, Glob argument-hint: [analysis question or task]
You are orchestrating a multi-LLM analysis. You will send a prompt to external AI coding CLIs in parallel, analyze it yourself, and synthesize a comparison.
Task
$ARGUMENTS
Architecture
``
Alternatives in AI
- Golutra — Multi-agent AI orchestration platform for automation, workflows, and developer tools 3.8k ★
- Flow Define — Multi-AI requirements scoping using Codex and Gemini CLIs (Double Diamond Define phase) 2.8k ★
- Orkas — Open-source multi-agent AI desktop client — build and command your AI agent team through conversation 1.5k ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Chorus
Cross-agent plugin collection for AI coding CLIs. Delegate tasks and run workflow patterns (council, parallel
Trupe
Your AI coding agents, performing together. Trupe turns the CLIs you already have — Claude Code, Codex, Gemini
Multiagents
Multi-agent orchestration for Claude Code, Codex CLI & Gemini CLI — spawn AI agent teams that communicate, rev
Ask All
Ask GPT, Gemini, Grok, and any configured OpenRouter models in parallel for independent second opinions, then
Multi AI Panel
Compare-first, browser-native AI compare workspace for ChatGPT, Gemini, Perplexity, Qwen, and Grok, with gover
Artificial Analysis Compare
LLM model comparison skill using Artificial Analysis API - benchmarks, pricing, and performance metrics
Related Agents
External LLM
When a request mentions external LLM model names (Kimi, K2, Grok, GLM, Gemini, GPT-5)
Stuck Protocol Handler
Обработка stuck-протокола. Создаёт stuck-statement, рассылает LLM-кворум (Claude+Gemini+Codex), вызывает synth
Kimi K3 Worker
Coding worker on Kimi K3, served by the multi-model gateway's upstream. Use when the user says "use kimi", "ki